Georgi Gerganov cad341d889 metal : reduce command encoding overhead (#9698) ...

* metal : reduce command encoding overhead

ggml-ci

* metal : add comments

2024-10-01 16:00:25 +03:00

..

baby-llama

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

batched

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

batched-bench

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

batched.swift

llama : llama_perf + option to disable timings during decode (#9355)

2024-09-13 09:53:38 +03:00

benchmark

ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)

2024-09-12 14:23:49 +03:00

convert-llama2c-to-ggml

vocab : refactor tokenizer to reduce init overhead (#9449)

2024-09-28 15:10:58 +03:00

cvector-generator

metal : reduce command encoding overhead (#9698)

2024-10-01 16:00:25 +03:00

deprecation-warning

…

embedding

llama : add reranking support (#9510)

2024-09-28 17:42:03 +03:00

eval-callback

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

export-lora

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

gbnf-validator

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

gen-docs

server : add more env vars, improve gen-docs (#9635)

2024-09-25 14:05:13 +02:00

gguf

…

gguf-hash

…

gguf-split

gguf-split : add basic checks (#9499)

2024-09-15 19:02:27 +02:00

gritlm

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

imatrix

imatrix : disable prompt escape by default (#9543)

2024-09-19 10:58:14 +03:00

infill

log : add CONT level for continuing previous log entry (#9610)

2024-09-24 10:15:35 +03:00

jeopardy

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

llama-bench

llama-bench: correct argument parsing error message (#9524)

2024-09-17 22:41:38 +02:00

llama.android

llama : minor sampling refactor (2) (#9386)

2024-09-09 17:10:46 +02:00

llama.swiftui

llama : minor sampling refactor (2) (#9386)

2024-09-09 17:10:46 +02:00

llava

metal : reduce command encoding overhead (#9698)

2024-10-01 16:00:25 +03:00

lookahead

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

lookup

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

main

log : add CONT level for continuing previous log entry (#9610)

2024-09-24 10:15:35 +03:00

main-cmake-pkg

…

parallel

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

passkey

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

perplexity

perplexity : remove extra new lines after chunks (#9596)

2024-09-23 11:28:02 +03:00

quantize

quantize : improve type name parsing (#9570)

2024-09-20 20:55:36 +02:00

quantize-stats

llama : refactor sampling v2 (#9294)

2024-09-07 15:16:19 +03:00

retrieval

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

rpc

readme : add LLMUnity to UI projects (#9381)

2024-09-09 14:21:38 +03:00

save-load-state

common : move arg parser code to arg.cpp (#9388)

2024-09-09 23:36:09 +02:00

server

py : update transfomers version (#9694)

2024-09-30 18:03:47 +03:00

simple

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

speculative

sampling : avoid expensive softmax during greedy sampling (#9605)

2024-09-24 09:03:17 +03:00

sycl

[SYCL]set context default value to avoid memory issue, update guide (#9476)

2024-09-18 08:30:31 +08:00

tokenize

common : reimplement logging (#9418)

2024-09-15 20:46:12 +03:00

base-translate.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

…

convert_legacy_llama.py

…

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

…

llama.vim

…

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar_examples.py

…

pydantic_models_to_grammar.py

…

reason-act.sh

…

regex_to_grammar.py

…

server_embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…